linux/fs/minix/inode.c

693 lines
18 KiB
C
Raw Normal View History

/*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Copyright (C) 1996 Gertjan van Wingerde
* Minix V2 fs support.
*
* Modified for 680x0 by Andreas Schwab
* Updated to filesystem version 3 by Daniel Aragones
*/
#include <linux/module.h>
#include "minix.h"
#include <linux/buffer_head.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/vfs.h>
#include <linux/writeback.h>
static int minix_write_inode(struct inode *inode,
struct writeback_control *wbc);
static int minix_statfs(struct dentry *dentry, struct kstatfs *buf);
static int minix_remount (struct super_block * sb, int * flags, char * data);
static void minix_evict_inode(struct inode *inode)
{
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 05:47:49 +08:00
truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
minix_truncate(inode);
}
invalidate_inode_buffers(inode);
clear_inode(inode);
if (!inode->i_nlink)
minix_free_inode(inode);
}
static void minix_put_super(struct super_block *sb)
{
int i;
struct minix_sb_info *sbi = minix_sb(sb);
if (!sb_rdonly(sb)) {
if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
sbi->s_ms->s_state = sbi->s_mount_state;
mark_buffer_dirty(sbi->s_sbh);
}
for (i = 0; i < sbi->s_imap_blocks; i++)
brelse(sbi->s_imap[i]);
for (i = 0; i < sbi->s_zmap_blocks; i++)
brelse(sbi->s_zmap[i]);
brelse (sbi->s_sbh);
kfree(sbi->s_imap);
sb->s_fs_info = NULL;
kfree(sbi);
}
static struct kmem_cache * minix_inode_cachep;
static struct inode *minix_alloc_inode(struct super_block *sb)
{
struct minix_inode_info *ei;
ei = kmem_cache_alloc(minix_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
}
2011-01-07 14:49:49 +08:00
static void minix_i_callback(struct rcu_head *head)
{
2011-01-07 14:49:49 +08:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(minix_inode_cachep, minix_i(inode));
}
2011-01-07 14:49:49 +08:00
static void minix_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, minix_i_callback);
}
static void init_once(void *foo)
{
struct minix_inode_info *ei = (struct minix_inode_info *) foo;
inode_init_once(&ei->vfs_inode);
}
static int __init init_inodecache(void)
{
minix_inode_cachep = kmem_cache_create("minix_inode_cache",
sizeof(struct minix_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
2016-01-15 07:18:21 +08:00
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
init_once);
if (minix_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(minix_inode_cachep);
}
static const struct super_operations minix_sops = {
.alloc_inode = minix_alloc_inode,
.destroy_inode = minix_destroy_inode,
.write_inode = minix_write_inode,
.evict_inode = minix_evict_inode,
.put_super = minix_put_super,
.statfs = minix_statfs,
.remount_fs = minix_remount,
};
static int minix_remount (struct super_block * sb, int * flags, char * data)
{
struct minix_sb_info * sbi = minix_sb(sb);
struct minix_super_block * ms;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
ms = sbi->s_ms;
if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb))
return 0;
if (*flags & MS_RDONLY) {
if (ms->s_state & MINIX_VALID_FS ||
!(sbi->s_mount_state & MINIX_VALID_FS))
return 0;
/* Mounting a rw partition read-only. */
if (sbi->s_version != MINIX_V3)
ms->s_state = sbi->s_mount_state;
mark_buffer_dirty(sbi->s_sbh);
} else {
/* Mount a partition which is read-only, read-write. */
if (sbi->s_version != MINIX_V3) {
sbi->s_mount_state = ms->s_state;
ms->s_state &= ~MINIX_VALID_FS;
} else {
sbi->s_mount_state = MINIX_VALID_FS;
}
mark_buffer_dirty(sbi->s_sbh);
if (!(sbi->s_mount_state & MINIX_VALID_FS))
printk("MINIX-fs warning: remounting unchecked fs, "
"running fsck is recommended\n");
else if ((sbi->s_mount_state & MINIX_ERROR_FS))
printk("MINIX-fs warning: remounting fs with errors, "
"running fsck is recommended\n");
}
return 0;
}
static int minix_fill_super(struct super_block *s, void *data, int silent)
{
struct buffer_head *bh;
struct buffer_head **map;
struct minix_super_block *ms;
struct minix3_super_block *m3s = NULL;
unsigned long i, block;
struct inode *root_inode;
struct minix_sb_info *sbi;
int ret = -EINVAL;
sbi = kzalloc(sizeof(struct minix_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
s->s_fs_info = sbi;
BUILD_BUG_ON(32 != sizeof (struct minix_inode));
BUILD_BUG_ON(64 != sizeof(struct minix2_inode));
if (!sb_set_blocksize(s, BLOCK_SIZE))
goto out_bad_hblock;
if (!(bh = sb_bread(s, 1)))
goto out_bad_sb;
ms = (struct minix_super_block *) bh->b_data;
sbi->s_ms = ms;
sbi->s_sbh = bh;
sbi->s_mount_state = ms->s_state;
sbi->s_ninodes = ms->s_ninodes;
sbi->s_nzones = ms->s_nzones;
sbi->s_imap_blocks = ms->s_imap_blocks;
sbi->s_zmap_blocks = ms->s_zmap_blocks;
sbi->s_firstdatazone = ms->s_firstdatazone;
sbi->s_log_zone_size = ms->s_log_zone_size;
sbi->s_max_size = ms->s_max_size;
s->s_magic = ms->s_magic;
if (s->s_magic == MINIX_SUPER_MAGIC) {
sbi->s_version = MINIX_V1;
sbi->s_dirsize = 16;
sbi->s_namelen = 14;
s->s_max_links = MINIX_LINK_MAX;
} else if (s->s_magic == MINIX_SUPER_MAGIC2) {
sbi->s_version = MINIX_V1;
sbi->s_dirsize = 32;
sbi->s_namelen = 30;
s->s_max_links = MINIX_LINK_MAX;
} else if (s->s_magic == MINIX2_SUPER_MAGIC) {
sbi->s_version = MINIX_V2;
sbi->s_nzones = ms->s_zones;
sbi->s_dirsize = 16;
sbi->s_namelen = 14;
s->s_max_links = MINIX2_LINK_MAX;
} else if (s->s_magic == MINIX2_SUPER_MAGIC2) {
sbi->s_version = MINIX_V2;
sbi->s_nzones = ms->s_zones;
sbi->s_dirsize = 32;
sbi->s_namelen = 30;
s->s_max_links = MINIX2_LINK_MAX;
} else if ( *(__u16 *)(bh->b_data + 24) == MINIX3_SUPER_MAGIC) {
m3s = (struct minix3_super_block *) bh->b_data;
s->s_magic = m3s->s_magic;
sbi->s_imap_blocks = m3s->s_imap_blocks;
sbi->s_zmap_blocks = m3s->s_zmap_blocks;
sbi->s_firstdatazone = m3s->s_firstdatazone;
sbi->s_log_zone_size = m3s->s_log_zone_size;
sbi->s_max_size = m3s->s_max_size;
sbi->s_ninodes = m3s->s_ninodes;
sbi->s_nzones = m3s->s_zones;
sbi->s_dirsize = 64;
sbi->s_namelen = 60;
sbi->s_version = MINIX_V3;
sbi->s_mount_state = MINIX_VALID_FS;
sb_set_blocksize(s, m3s->s_blocksize);
s->s_max_links = MINIX2_LINK_MAX;
} else
goto out_no_fs;
/*
* Allocate the buffer map to keep the superblock small.
*/
if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
goto out_illegal_sb;
i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh);
map = kzalloc(i, GFP_KERNEL);
if (!map)
goto out_no_map;
sbi->s_imap = &map[0];
sbi->s_zmap = &map[sbi->s_imap_blocks];
block=2;
for (i=0 ; i < sbi->s_imap_blocks ; i++) {
if (!(sbi->s_imap[i]=sb_bread(s, block)))
goto out_no_bitmap;
block++;
}
for (i=0 ; i < sbi->s_zmap_blocks ; i++) {
if (!(sbi->s_zmap[i]=sb_bread(s, block)))
goto out_no_bitmap;
block++;
}
minix_set_bit(0,sbi->s_imap[0]->b_data);
minix_set_bit(0,sbi->s_zmap[0]->b_data);
/* Apparently minix can create filesystems that allocate more blocks for
* the bitmaps than needed. We simply ignore that, but verify it didn't
* create one with not enough blocks and bail out if so.
*/
block = minix_blocks_needed(sbi->s_ninodes, s->s_blocksize);
if (sbi->s_imap_blocks < block) {
printk("MINIX-fs: file system does not have enough "
"imap blocks allocated. Refusing to mount.\n");
goto out_no_bitmap;
}
block = minix_blocks_needed(
(sbi->s_nzones - sbi->s_firstdatazone + 1),
s->s_blocksize);
if (sbi->s_zmap_blocks < block) {
printk("MINIX-fs: file system does not have enough "
"zmap blocks allocated. Refusing to mount.\n");
goto out_no_bitmap;
}
/* set up enough so that it can read an inode */
s->s_op = &minix_sops;
root_inode = minix_iget(s, MINIX_ROOT_INO);
if (IS_ERR(root_inode)) {
ret = PTR_ERR(root_inode);
goto out_no_root;
}
ret = -ENOMEM;
s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto out_no_root;
if (!sb_rdonly(s)) {
if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
ms->s_state &= ~MINIX_VALID_FS;
mark_buffer_dirty(bh);
}
if (!(sbi->s_mount_state & MINIX_VALID_FS))
printk("MINIX-fs: mounting unchecked file system, "
"running fsck is recommended\n");
else if (sbi->s_mount_state & MINIX_ERROR_FS)
printk("MINIX-fs: mounting file system with errors, "
"running fsck is recommended\n");
return 0;
out_no_root:
if (!silent)
printk("MINIX-fs: get root inode failed\n");
goto out_freemap;
out_no_bitmap:
printk("MINIX-fs: bad superblock or unable to read bitmaps\n");
out_freemap:
for (i = 0; i < sbi->s_imap_blocks; i++)
brelse(sbi->s_imap[i]);
for (i = 0; i < sbi->s_zmap_blocks; i++)
brelse(sbi->s_zmap[i]);
kfree(sbi->s_imap);
goto out_release;
out_no_map:
ret = -ENOMEM;
if (!silent)
printk("MINIX-fs: can't allocate map\n");
goto out_release;
out_illegal_sb:
if (!silent)
printk("MINIX-fs: bad superblock\n");
goto out_release;
out_no_fs:
if (!silent)
printk("VFS: Can't find a Minix filesystem V1 | V2 | V3 "
"on device %s.\n", s->s_id);
out_release:
brelse(bh);
goto out;
out_bad_hblock:
printk("MINIX-fs: blocksize too small for device\n");
goto out;
out_bad_sb:
printk("MINIX-fs: unable to read superblock\n");
out:
s->s_fs_info = NULL;
kfree(sbi);
return ret;
}
static int minix_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct minix_sb_info *sbi = minix_sb(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = sb->s_magic;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = (sbi->s_nzones - sbi->s_firstdatazone) << sbi->s_log_zone_size;
buf->f_bfree = minix_count_free_blocks(sb);
buf->f_bavail = buf->f_bfree;
buf->f_files = sbi->s_ninodes;
buf->f_ffree = minix_count_free_inodes(sb);
buf->f_namelen = sbi->s_namelen;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
static int minix_get_block(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int create)
{
if (INODE_VERSION(inode) == MINIX_V1)
return V1_minix_get_block(inode, block, bh_result, create);
else
return V2_minix_get_block(inode, block, bh_result, create);
}
static int minix_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, minix_get_block, wbc);
}
static int minix_readpage(struct file *file, struct page *page)
{
return block_read_full_page(page,minix_get_block);
}
int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len)
{
return __block_write_begin(page, pos, len, minix_get_block);
}
static void minix_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
if (to > inode->i_size) {
truncate_pagecache(inode, inode->i_size);
minix_truncate(inode);
}
}
static int minix_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
int ret;
ret = block_write_begin(mapping, pos, len, flags, pagep,
minix_get_block);
if (unlikely(ret))
minix_write_failed(mapping, pos + len);
return ret;
}
static sector_t minix_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,minix_get_block);
}
static const struct address_space_operations minix_aops = {
.readpage = minix_readpage,
.writepage = minix_writepage,
.write_begin = minix_write_begin,
.write_end = generic_write_end,
.bmap = minix_bmap
};
static const struct inode_operations minix_symlink_inode_operations = {
.get_link = page_get_link,
.getattr = minix_getattr,
};
void minix_set_inode(struct inode *inode, dev_t rdev)
{
if (S_ISREG(inode->i_mode)) {
inode->i_op = &minix_file_inode_operations;
inode->i_fop = &minix_file_operations;
inode->i_mapping->a_ops = &minix_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &minix_dir_inode_operations;
inode->i_fop = &minix_dir_operations;
inode->i_mapping->a_ops = &minix_aops;
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &minix_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &minix_aops;
} else
init_special_inode(inode, inode->i_mode, rdev);
}
/*
* The minix V1 function to read an inode.
*/
static struct inode *V1_minix_iget(struct inode *inode)
{
struct buffer_head * bh;
struct minix_inode * raw_inode;
struct minix_inode_info *minix_inode = minix_i(inode);
int i;
raw_inode = minix_V1_raw_inode(inode->i_sb, inode->i_ino, &bh);
if (!raw_inode) {
iget_failed(inode);
return ERR_PTR(-EIO);
}
inode->i_mode = raw_inode->i_mode;
i_uid_write(inode, raw_inode->i_uid);
i_gid_write(inode, raw_inode->i_gid);
set_nlink(inode, raw_inode->i_nlinks);
inode->i_size = raw_inode->i_size;
inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = raw_inode->i_time;
inode->i_mtime.tv_nsec = 0;
inode->i_atime.tv_nsec = 0;
inode->i_ctime.tv_nsec = 0;
inode->i_blocks = 0;
for (i = 0; i < 9; i++)
minix_inode->u.i1_data[i] = raw_inode->i_zone[i];
minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0]));
brelse(bh);
unlock_new_inode(inode);
return inode;
}
/*
* The minix V2 function to read an inode.
*/
static struct inode *V2_minix_iget(struct inode *inode)
{
struct buffer_head * bh;
struct minix2_inode * raw_inode;
struct minix_inode_info *minix_inode = minix_i(inode);
int i;
raw_inode = minix_V2_raw_inode(inode->i_sb, inode->i_ino, &bh);
if (!raw_inode) {
iget_failed(inode);
return ERR_PTR(-EIO);
}
inode->i_mode = raw_inode->i_mode;
i_uid_write(inode, raw_inode->i_uid);
i_gid_write(inode, raw_inode->i_gid);
set_nlink(inode, raw_inode->i_nlinks);
inode->i_size = raw_inode->i_size;
inode->i_mtime.tv_sec = raw_inode->i_mtime;
inode->i_atime.tv_sec = raw_inode->i_atime;
inode->i_ctime.tv_sec = raw_inode->i_ctime;
inode->i_mtime.tv_nsec = 0;
inode->i_atime.tv_nsec = 0;
inode->i_ctime.tv_nsec = 0;
inode->i_blocks = 0;
for (i = 0; i < 10; i++)
minix_inode->u.i2_data[i] = raw_inode->i_zone[i];
minix_set_inode(inode, old_decode_dev(raw_inode->i_zone[0]));
brelse(bh);
unlock_new_inode(inode);
return inode;
}
/*
* The global function to read an inode.
*/
struct inode *minix_iget(struct super_block *sb, unsigned long ino)
{
struct inode *inode;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
if (INODE_VERSION(inode) == MINIX_V1)
return V1_minix_iget(inode);
else
return V2_minix_iget(inode);
}
/*
* The minix V1 function to synchronize an inode.
*/
static struct buffer_head * V1_minix_update_inode(struct inode * inode)
{
struct buffer_head * bh;
struct minix_inode * raw_inode;
struct minix_inode_info *minix_inode = minix_i(inode);
int i;
raw_inode = minix_V1_raw_inode(inode->i_sb, inode->i_ino, &bh);
if (!raw_inode)
return NULL;
raw_inode->i_mode = inode->i_mode;
raw_inode->i_uid = fs_high2lowuid(i_uid_read(inode));
raw_inode->i_gid = fs_high2lowgid(i_gid_read(inode));
raw_inode->i_nlinks = inode->i_nlink;
raw_inode->i_size = inode->i_size;
raw_inode->i_time = inode->i_mtime.tv_sec;
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_zone[0] = old_encode_dev(inode->i_rdev);
else for (i = 0; i < 9; i++)
raw_inode->i_zone[i] = minix_inode->u.i1_data[i];
mark_buffer_dirty(bh);
return bh;
}
/*
* The minix V2 function to synchronize an inode.
*/
static struct buffer_head * V2_minix_update_inode(struct inode * inode)
{
struct buffer_head * bh;
struct minix2_inode * raw_inode;
struct minix_inode_info *minix_inode = minix_i(inode);
int i;
raw_inode = minix_V2_raw_inode(inode->i_sb, inode->i_ino, &bh);
if (!raw_inode)
return NULL;
raw_inode->i_mode = inode->i_mode;
raw_inode->i_uid = fs_high2lowuid(i_uid_read(inode));
raw_inode->i_gid = fs_high2lowgid(i_gid_read(inode));
raw_inode->i_nlinks = inode->i_nlink;
raw_inode->i_size = inode->i_size;
raw_inode->i_mtime = inode->i_mtime.tv_sec;
raw_inode->i_atime = inode->i_atime.tv_sec;
raw_inode->i_ctime = inode->i_ctime.tv_sec;
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_zone[0] = old_encode_dev(inode->i_rdev);
else for (i = 0; i < 10; i++)
raw_inode->i_zone[i] = minix_inode->u.i2_data[i];
mark_buffer_dirty(bh);
return bh;
}
static int minix_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err = 0;
struct buffer_head *bh;
if (INODE_VERSION(inode) == MINIX_V1)
bh = V1_minix_update_inode(inode);
else
bh = V2_minix_update_inode(inode);
if (!bh)
return -EIO;
if (wbc->sync_mode == WB_SYNC_ALL && buffer_dirty(bh)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
printk("IO error syncing minix inode [%s:%08lx]\n",
inode->i_sb->s_id, inode->i_ino);
err = -EIO;
}
}
brelse (bh);
return err;
}
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
int minix_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
struct super_block *sb = path->dentry->d_sb;
struct inode *inode = d_inode(path->dentry);
generic_fillattr(inode, stat);
if (INODE_VERSION(inode) == MINIX_V1)
stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb);
else
stat->blocks = (sb->s_blocksize / 512) * V2_minix_blocks(stat->size, sb);
stat->blksize = sb->s_blocksize;
return 0;
}
/*
* The function that is called for file truncation.
*/
void minix_truncate(struct inode * inode)
{
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)))
return;
if (INODE_VERSION(inode) == MINIX_V1)
V1_minix_truncate(inode);
else
V2_minix_truncate(inode);
}
static struct dentry *minix_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, minix_fill_super);
}
static struct file_system_type minix_fs_type = {
.owner = THIS_MODULE,
.name = "minix",
.mount = minix_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("minix");
static int __init init_minix_fs(void)
{
int err = init_inodecache();
if (err)
goto out1;
err = register_filesystem(&minix_fs_type);
if (err)
goto out;
return 0;
out:
destroy_inodecache();
out1:
return err;
}
static void __exit exit_minix_fs(void)
{
unregister_filesystem(&minix_fs_type);
destroy_inodecache();
}
module_init(init_minix_fs)
module_exit(exit_minix_fs)
MODULE_LICENSE("GPL");